| plbert_params: | |
| vocab_size: 198 | |
| hidden_size: 768 | |
| num_attention_heads: 12 | |
| intermediate_size: 2048 | |
| max_position_embeddings: 512 | |
| num_hidden_layers: 12 | |
| dropout: 0.1 | |
| model_params: | |
| multispeaker: true | |
| vocab: "$-´;:,.!?¡¿—…\"«»“” ()†/=ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyzéýíó'̯'͡ɑɐɒæɓʙβɔɕçɗɖðʤəɘɚɛɜɝɞɟʄɡɠɢʛɦɧħɥʜɨɪʝɭɬɫɮʟɱɯɰŋɳɲɴøɵɸθœɶʘɹɺɾɻʀʁɽʂʃʈʧʉʊʋⱱʌɣɤʍχʎʏʑʐʒʔʡʕʢǀǁǂǃˈˌːˑʼʴʰʱʲ'̩'ᵻ" | |
| dim_in: 64 | |
| hidden_dim: 512 | |
| max_conv_dim: 512 | |
| n_layer: 3 | |
| n_mels: 80 | |
| n_token: 181 # number of phoneme tokens | |
| max_dur: 50 # maximum duration of a single phoneme | |
| style_dim: 128 # style vector size | |
| dropout: 0.0 | |
| # config for decoder | |
| decoder: | |
| type: 'istftnet' # either hifigan or istftnet | |
| resblock_kernel_sizes: [3,7,11] | |
| upsample_rates : [10, 6] | |
| upsample_initial_channel: 512 | |
| resblock_dilation_sizes: [[1,3,5], [1,3,5], [1,3,5]] | |
| upsample_kernel_sizes: [20, 12] | |
| gen_istft_n_fft: 20 | |
| gen_istft_hop_size: 5 | |
| # style diffusion model config | |
| diffusion: | |
| embedding_mask_proba: 0.1 | |
| # transformer config | |
| transformer: | |
| num_layers: 3 | |
| num_heads: 8 | |
| head_features: 64 | |
| multiplier: 2 | |
| # diffusion distribution config | |
| dist: | |
| sigma_data: 0.18 | |
| mean: -4.0 | |
| std: 4.0 | |
| asr_params: | |
| input_dim: 80 | |
| hidden_dim: 256 | |
| n_token: 181 | |
| token_embedding_dim: 512 |